Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8961
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Egyptian politics, particularly focusing on the name "Mohamed Morsi" and "Trey"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and health-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stadium
    -0.71
    arna
    -0.68
     Milan
    -0.68
     Genetics
    -0.66
     Barcl
    -0.65
     CENT
    -0.64
     Eva
    -0.64
     CARD
    -0.63
     Burger
    -0.63
     Esp
    -0.63
    POSITIVE LOGITS
    ogly
    0.99
    artisan
    0.94
    uable
    0.93
    iquid
    0.83
    lections
    0.82
    vironment
    0.82
    cair
    0.82
    osph
    0.81
    ideshow
    0.77
    lect
    0.77
    Activations Density 0.026%

    No Known Activations